Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and investigative activities

    oai_token-act-pair · gpt-3.5-turbo

    words that convey specific characteristics or qualities, particularly focusing on suffixes that imply a state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.83
    chwitz
    -0.82
    cius
    -0.76
    isSpecialOrderable
    -0.75
    arte
    -0.74
    OPA
    -0.72
    ynthesis
    -0.72
    azel
    -0.71
    ARC
    -0.70
    Rah
    -0.70
    POSITIVE LOGITS
    ly
    0.94
    ness
    0.91
     pursuit
    0.85
     settlement
    0.83
     seas
    0.83
    hearted
    0.82
    nesses
    0.79
    ity
    0.78
     streak
    0.77
    lly
    0.75
    Act Density 0.178%

    No Known Activations